Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1085 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2761. Min Range: -0.2761

Max Act: 0.2761. Min Act: -0.0000

Data Index: 897806 (C4 (Web Text))

Max Activating Token Index: 235

Text #1

Max Range: 0.2761. Min Range: -0.2761

Max Act: 0.2693. Min Act: -0.0001

Data Index: 302676 (C4 (Web Text))

Max Activating Token Index: 82

Text #2

Max Range: 0.2761. Min Range: -0.2761

Max Act: 0.2518. Min Act: -0.0000

Data Index: 457318 (C4 (Web Text))

Max Activating Token Index: 751

Text #3

Max Range: 0.2761. Min Range: -0.2761

Max Act: 0.2162. Min Act: -0.0001

Data Index: 565869 (C4 (Web Text))

Max Activating Token Index: 607

Text #4

Max Range: 0.2761. Min Range: -0.2761

Max Act: 0.2351. Min Act: -0.0000

Data Index: 490047 (C4 (Web Text))

Max Activating Token Index: 59

Text #5

Max Range: 0.2761. Min Range: -0.2761

Max Act: 0.2335. Min Act: -0.0000

Data Index: 819394 (C4 (Web Text))

Max Activating Token Index: 472

Text #6

Max Range: 0.2761. Min Range: -0.2761

Max Act: 0.2335. Min Act: -0.0000

Data Index: 678460 (C4 (Web Text))

Max Activating Token Index: 736

Text #7

Max Range: 0.2761. Min Range: -0.2761

Max Act: 0.2321. Min Act: -0.0001

Data Index: 88946 (C4 (Web Text))

Max Activating Token Index: 806

Text #8

Max Range: 0.2761. Min Range: -0.2761

Max Act: 0.2466. Min Act: -0.0001

Data Index: 79472 (C4 (Web Text))

Max Activating Token Index: 90

Text #9

Max Range: 0.2761. Min Range: -0.2761

Max Act: 0.2386. Min Act: -0.0001

Data Index: 735391 (C4 (Web Text))

Max Activating Token Index: 100

Text #10

Max Range: 0.2761. Min Range: -0.2761

Max Act: 0.2255. Min Act: -0.0000

Data Index: 443775 (C4 (Web Text))

Max Activating Token Index: 715

Text #11

Max Range: 0.2761. Min Range: -0.2761

Max Act: 0.2254. Min Act: -0.0000

Data Index: 538835 (C4 (Web Text))

Max Activating Token Index: 330

Text #12

Max Range: 0.2761. Min Range: -0.2761

Max Act: 0.2151. Min Act: -0.0001

Data Index: 1183785 (C4 (Web Text))

Max Activating Token Index: 812

Text #13

Max Range: 0.2761. Min Range: -0.2761

Max Act: 0.2300. Min Act: -0.0000

Data Index: 859438 (C4 (Web Text))

Max Activating Token Index: 71

Text #14

Max Range: 0.2761. Min Range: -0.2761

Max Act: 0.2421. Min Act: -0.0000

Data Index: 91446 (C4 (Web Text))

Max Activating Token Index: 699

Text #15

Max Range: 0.2761. Min Range: -0.2761

Max Act: 0.1962. Min Act: -0.0000

Data Index: 480196 (C4 (Web Text))

Max Activating Token Index: 880

Text #16

Max Range: 0.2761. Min Range: -0.2761

Max Act: 0.2120. Min Act: -0.0000

Data Index: 65318 (C4 (Web Text))

Max Activating Token Index: 248

Text #17

Max Range: 0.2761. Min Range: -0.2761

Max Act: 0.2176. Min Act: -0.0000

Data Index: 1040593 (C4 (Web Text))

Max Activating Token Index: 932

Text #18

Max Range: 0.2761. Min Range: -0.2761

Max Act: 0.2089. Min Act: -0.0000

Data Index: 409738 (C4 (Web Text))

Max Activating Token Index: 587

Text #19

Max Range: 0.2761. Min Range: -0.2761

Max Act: 0.1879. Min Act: -0.0000

Data Index: 1340704 (C4 (Web Text))

Max Activating Token Index: 776